II.
Benchmark JSON
Structured · livebenchmark:swe-lancer
SWE-Lancer json
Inspect the normalized record payload exactly as the atlas UI reads it.
{
"id": "benchmark:swe-lancer",
"_kind": "Benchmark",
"_file": "benchmarks/benchmarks/benchmarks-coding.yaml",
"_cluster": "benchmarks",
"attributes": {
"displayName": "SWE-Lancer",
"homepageUrl": "https://github.com/openai/SWELancer-Benchmark",
"kind": "full-stack",
"targetsKind": "AgentVersion",
"description": "OpenAI benchmark of >1,400 paid freelance software-engineering tasks\nscraped from Upwork, with associated bounties. Measures end-to-end\nagent ability to deliver shippable freelance work.\n"
},
"outgoingEdges": [
{
"from": "benchmark:swe-lancer",
"to": "skill-area:autonomous-coding-engagement",
"kind": "covers",
"attributes": {
"attributes": {
"coverage": "full",
"weight": 0.7
}
}
},
{
"from": "benchmark:swe-lancer",
"to": "skill-area:bug-fixing-from-issues",
"kind": "covers",
"attributes": {
"attributes": {
"coverage": "partial",
"weight": 0.2
}
}
},
{
"from": "benchmark:swe-lancer",
"to": "domain:software-engineering",
"kind": "applies_to",
"attributes": {}
}
],
"incomingEdges": []
}